honest-review

Research-driven code review. Every finding validated with evidence. 4-wave pipeline: Triage → Analysis → Research → Judge.

| Empty + changes in session (git diff) | Session review of changed files | | Empty + no changes (first message) | Full codebase audit | | File or directory path | Scoped review of that path | | "audit" | Force full codebase audit | | PR number/URL | Review PR changes (gh pr diff) | | Git range (HEAD3..HEAD) | Review changes in that range |

Confidence-calibrated reporting: Every finding carries a confidence score (0.0-1.0). Confidence ≥ 0.7: report. Confidence 0.3-0.7: report as "unconfirmed". Confidence < 0.3: discard (except P0/S0).

研究驱动的多个抽象级别的代码审查，包括优势认可、创意审查镜头、人工智能代码气味检测以及按项目类型进行的严重性校准。两种模式：（1）会议审查——使用平行审查者审查和验证变更，研究验证每个假设； (2) 完整的代码库审计——使用由子代理生成的审核者组成的平行团队进行深入的端到端评估。在审查变更、验证工作质量、审核代码库、验证正确性、检查假设、发现缺陷、降低复杂性时使用。不适用于编写新代码、解释代码或基准测试。 来源：wyattowalsh/agents。